# Machine Translation Evaluation on WMT segment-level 2019 (test) Source: [Machine Translation Evaluation on WMT segment-level 2019 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:57:43.615Z Evaluation of machine translation quality on the WMT 2019 segment-level test set, measured using correlation metrics such as Pearson's R. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Machine Translation Evaluation | | Dataset (including any stated split) | WMT segment-level 2019 (test) | | Metric | Pearson R | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 19 of 19 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Pearson R](): Higher is better; unit: PERCENT. ## Recorded results | Method | Pearson R | Result date | Report paper | | --- | --- | --- | --- | | BERTScore | 44.5 | Not recorded | 68fa6b131e209131cea2bfd7 | | MoverScore | 44 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 43.6 | Not recorded | 68fa6b131e209131cea2bfd7 | | BERTScore | 43.2 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 43 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 42.8 | Not recorded | 68fa6b131e209131cea2bfd7 | | BERTScore | 41.9 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 41.9 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 41.7 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 41.5 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 41.3 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 40.5 | Not recorded | 68fa6b131e209131cea2bfd7 | | BERTScore | 39.8 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 39.8 | Not recorded | 68fa6b131e209131cea2bfd7 | | BERTScore | 39.1 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 38.4 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 38 | Not recorded | 68fa6b131e209131cea2bfd7 | | BERTScore | 37.6 | Not recorded | 68fa6b131e209131cea2bfd7 | | FrugalScore | 37.5 | Not recorded | 68fa6b131e209131cea2bfd7 | ### BERTScore Pearson R: 44.5. Result ID: 698e5310ffc3901de09ca1ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"DeBERTa-XLarge","Params":"900M","Runtime":"3m 49s"}. This record does not assert independent reproduction. ### MoverScore Pearson R: 44. Result ID: 698e5310ffc3901de09ca1cb. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BERT-Base","Params":"110M","Runtime":"64m 32s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 43.6. Result ID: 698e5310ffc3901de09ca1d7. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Medium","Teacher":"MoverScore (BERT-Base)","Params":"41.7M","Runtime":"1m 55s"}. This record does not assert independent reproduction. ### BERTScore Pearson R: 43.2. Result ID: 698e5310ffc3901de09ca1c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"RoBERTa-Large","Params":"355M","Runtime":"3m 03s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 43. Result ID: 698e5310ffc3901de09ca1d4. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Medium","Teacher":"BERTScore (DeBERTa-XLarge)","Params":"41.7M","Runtime":"1m 55s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 42.8. Result ID: 698e5310ffc3901de09ca1d6. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Small","Teacher":"MoverScore (BERT-Base)","Params":"29.1M","Runtime":"1m 35s"}. This record does not assert independent reproduction. ### BERTScore Pearson R: 41.9. Result ID: 698e5310ffc3901de09ca1c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BERT-Base","Params":"110M","Runtime":"2m 09s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 41.9. Result ID: 698e5310ffc3901de09ca1ce. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Medium","Teacher":"BERTScore (BERT-Base)","Params":"41.7M","Runtime":"1m 55s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 41.7. Result ID: 698e5310ffc3901de09ca1d1. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Medium","Teacher":"BERTScore (RoBERTa-Large)","Params":"41.7M","Runtime":"1m 55s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 41.5. Result ID: 698e5310ffc3901de09ca1d3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Small","Teacher":"BERTScore (DeBERTa-XLarge)","Params":"29.1M","Runtime":"1m 35s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 41.3. Result ID: 698e5310ffc3901de09ca1cd. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Small","Teacher":"BERTScore (BERT-Base)","Params":"29.1M","Runtime":"1m 35s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 40.5. Result ID: 698e5310ffc3901de09ca1d0. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Small","Teacher":"BERTScore (RoBERTa-Large)","Params":"29.1M","Runtime":"1m 35s"}. This record does not assert independent reproduction. ### BERTScore Pearson R: 39.8. Result ID: 698e5310ffc3901de09ca1c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BERT-Medium","Params":"41.7M","Runtime":"2m 04s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 39.8. Result ID: 698e5310ffc3901de09ca1d5. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Tiny","Teacher":"MoverScore (BERT-Base)","Params":"4.4M","Runtime":"1m 18s"}. This record does not assert independent reproduction. ### BERTScore Pearson R: 39.1. Result ID: 698e5310ffc3901de09ca1c6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BERT-Small","Params":"29.1M","Runtime":"1m 42s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 38.4. Result ID: 698e5310ffc3901de09ca1cc. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Tiny","Teacher":"BERTScore (BERT-Base)","Params":"4.4M","Runtime":"1m 18s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 38. Result ID: 698e5310ffc3901de09ca1d2. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Tiny","Teacher":"BERTScore (DeBERTa-XLarge)","Params":"4.4M","Runtime":"1m 18s"}. This record does not assert independent reproduction. ### BERTScore Pearson R: 37.6. Result ID: 698e5310ffc3901de09ca1c5. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Backbone":"BERT-Tiny","Params":"4.4M","Runtime":"1m 22s"}. This record does not assert independent reproduction. ### FrugalScore Pearson R: 37.5. Result ID: 698e5310ffc3901de09ca1cf. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Backbone":"BERT-Tiny","Teacher":"BERTScore (RoBERTa-Large)","Params":"4.4M","Runtime":"1m 18s"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.